mirror of
https://gitlab.freedesktop.org/uchardet/uchardet.git
synced 2025-12-07 01:06:40 +08:00
fbd2efdbe9
Encodings: ISO-8859-2, ISO-8859-16, Windows-1250 and IBM852. Test texts from https://ro.wikipedia.org/wiki/Danemarca
66 lines
2.5 KiB
Python
66 lines
2.5 KiB
Python
#!/bin/python3
|
|
# -*- coding: utf-8 -*-
|
|
|
|
# ##### BEGIN LICENSE BLOCK #####
|
|
# Version: MPL 1.1/GPL 2.0/LGPL 2.1
|
|
#
|
|
# The contents of this file are subject to the Mozilla Public License Version
|
|
# 1.1 (the "License"); you may not use this file except in compliance with
|
|
# the License. You may obtain a copy of the License at
|
|
# http://www.mozilla.org/MPL/
|
|
#
|
|
# Software distributed under the License is distributed on an "AS IS" basis,
|
|
# WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
|
|
# for the specific language governing rights and limitations under the
|
|
# License.
|
|
#
|
|
# The Original Code is Mozilla Universal charset detector code.
|
|
#
|
|
# The Initial Developer of the Original Code is
|
|
# Netscape Communications Corporation.
|
|
# Portions created by the Initial Developer are Copyright (C) 2001
|
|
# the Initial Developer. All Rights Reserved.
|
|
#
|
|
# Contributor(s):
|
|
# Jehan <jehan@girinstud.io>
|
|
#
|
|
# Alternatively, the contents of this file may be used under the terms of
|
|
# either the GNU General Public License Version 2 or later (the "GPL"), or
|
|
# the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
|
|
# in which case the provisions of the GPL or the LGPL are applicable instead
|
|
# of those above. If you wish to allow use of your version of this file only
|
|
# under the terms of either the GPL or the LGPL, and not to allow others to
|
|
# use your version of this file under the terms of the MPL, indicate your
|
|
# decision by deleting the provisions above and replace them with the notice
|
|
# and other provisions required by the GPL or the LGPL. If you do not delete
|
|
# the provisions above, a recipient may use your version of this file under
|
|
# the terms of any one of the MPL, the GPL or the LGPL.
|
|
#
|
|
# ##### END LICENSE BLOCK #####
|
|
|
|
import re
|
|
|
|
## Mandatory Properties ##
|
|
|
|
name = 'Romanian'
|
|
code = 'ro'
|
|
use_ascii = True
|
|
charsets = ['ISO-8859-2', 'ISO-8859-16',
|
|
'Windows-1250', 'IBM852']
|
|
|
|
## Optional Properties ##
|
|
|
|
# Alphabet characters.
|
|
# Note: Wikipedia explains that s and t with cedilla (şţ), or even
|
|
# bare s and t, were often used in place of s and t with comma (șț)
|
|
# because of missing characters in most common encoding at the time.
|
|
# It may be worth adding some common_replacement_letters logics in
|
|
# the training and models.
|
|
# https://en.wikipedia.org/wiki/Romanian_alphabet#ISO_8859
|
|
alphabet = 'ăâîșț'
|
|
# The starred page which was rewarded on the main page when I created
|
|
# the data.
|
|
start_pages = ['The Loving Kind']
|
|
wikipedia_code = code
|
|
case_mapping = True
|